Crimson AI NewsA CrimsonLingua Network service
EN ع
← Back to news
Research paper Hugging Face

Deterministic Screen-Activity Compiler Turns Agent Memory into Auditable, Replayable Frames

AI By Crimson AI Hugging Face Papers 7 August 2026 · 00:00 9 views
Share: X Telegram

A new zero-model pipeline compiles passively captured screen activity into typed, byte-identical memory frames, cutting context size by 86x and boosting question-answering accuracy to 98.4%, while enabling zero-token replay of recurring routines.

Deterministic Screen-Activity Compiler Turns Agent Memory into Auditable, Replayable Frames

Key points

Computer-use agents often waste expensive frontier inference re-deriving routines the user has already performed, because their memory records what was said, not what was done. A new paper from Hugging Face introduces Activity Frames, a deterministic, zero-model compiler that turns locally captured screen activity into structured agent memory.

The pipeline segments a local capture stream into typed activity frames—bounded episodes carrying application, site, timing, input volume, and evidence pointers back to raw rows. With no model in the loop, the output is byte-identical, cacheable, and mechanically auditable, a stark contrast to typical vector-store-based memory systems.

In a single-user corpus of 128,756 frames over 51 active days, the compiler reduces a day of raw capture to a context block 86x smaller in 68 ms. An agent reading that block answers questions about the day at 98.4% accuracy (Wilson 95% CI 91.7-99.7%), versus 66-80% for an LLM summary of the same capture. Notably, a mid-tier model reading the block matches a frontier model.

The compiler also serves as a demand-side cost instrument, measuring two parameters previously assumed but unmeasured in agent-cost models: the Routine Overhead Ratio R (60-343x, a modeled upper bound) and delegable recurrence (9.0% in-sample, 7.7% out-of-sample), implying an all-fleet token ceiling near 8%. A compiled routine replays deterministically with the model out of the loop, demonstrated live at zero model tokens on a guard-matched hit.

The authors acknowledge trade-offs: replay is for "same task, new values," and intent is deliberately excluded from the measured tier. Drift across UI states is handled via per-step guards that hand back to the model on mismatch. The schema, compiler, and evaluation harness are open-sourced under MIT.

MetricValue
Context size reduction86x
Compilation time68 ms per day
QA accuracy (Activity Frames)98.4% (95% CI 91.7-99.7%)
QA accuracy (LLM summary)66-80%
Routine Overhead Ratio R60-343x (modeled upper bound)
Delegable recurrence (in-sample)9.0%
Delegable recurrence (out-of-sample)7.7%
All-fleet token ceiling~8%
Source
Hugging Face · Hugging Face Papers
Related news
Research paper
Hugging Face 31 Aug 2026

Hugging Face Unveils StepGuard: Step-Level Guardrails for Safer AI Agents

StepGuard, a new step-level guard model from Hugging Face, audits agent actions before execution, reducing attack success rates by...

1
Research paper
Hugging Face 31 Aug 2026

Hugging Face Researchers Unveil ABot-Recon for Stable Long-Horizon 3D Reconstruction

ABot-Recon, a new streaming 3D reconstruction model from Hugging Face, achieves stable long-horizon performance using only local t...

1
Research paper
Hugging Face 31 Aug 2026

ContextPilot: Teaching Agents Proactive Context Management via Fine-Grained RL

Hugging Face researchers introduce ContextPilot, a framework that enhances long-horizon agent reasoning by expanding context-editi...

1